FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951952347> ?p ?o ?g. }

• W2951952347 abstract "We introduce a novel self-supervised learning method based on adversarial training. Our objective is to train a discriminator network to distinguish real images from images with synthetic artifacts, and then to extract features from its intermediate layers that can be transferred to other data domains and tasks. To generate images with artifacts, we pre-train a high-capacity autoencoder and then we use a damage and repair strategy: First, we freeze the autoencoder and damage the output of the encoder by randomly dropping its entries. Second, we augment the decoder with a repair network, and train it in an adversarial manner against the discriminator. The repair network helps generate more realistic images by inpainting the dropped feature entries. To make the discriminator focus on the artifacts, we also make it predict what entries in the feature were dropped. We demonstrate experimentally that features learned by creating and spotting artifacts achieve state of the art performance in several benchmarks." @default.
• W2951952347 created "2019-06-27" @default.
• W2951952347 creator A5070714354 @default.
• W2951952347 creator A5070940574 @default.
• W2951952347 date "2018-06-13" @default.
• W2951952347 modified "2023-09-27" @default.
• W2951952347 title "Self-Supervised Feature Learning by Learning to Spot Artifacts" @default.
• W2951952347 cites W1522301498 @default.
• W2951952347 cites W1825675169 @default.
• W2951952347 cites W2099471712 @default.
• W2951952347 cites W2108598243 @default.
• W2951952347 cites W2113145584 @default.
• W2951952347 cites W2118858186 @default.
• W2951952347 cites W2134670479 @default.
• W2951952347 cites W2145094598 @default.
• W2951952347 cites W2148349024 @default.
• W2951952347 cites W2173520492 @default.
• W2951952347 cites W2198618282 @default.
• W2951952347 cites W2267038056 @default.
• W2951952347 cites W2287334441 @default.
• W2951952347 cites W2295936755 @default.
• W2951952347 cites W2321533354 @default.
• W2951952347 cites W2326925005 @default.
• W2951952347 cites W2338684808 @default.
• W2951952347 cites W2342877626 @default.
• W2951952347 cites W2412320034 @default.
• W2951952347 cites W2432004435 @default.
• W2951952347 cites W2511428026 @default.
• W2951952347 cites W2519998487 @default.
• W2951952347 cites W2556707115 @default.
• W2951952347 cites W2949117887 @default.
• W2951952347 cites W2949532563 @default.
• W2951952347 cites W2949650786 @default.
• W2951952347 cites W2949891561 @default.
• W2951952347 cites W2950187998 @default.
• W2951952347 cites W2950341389 @default.
• W2951952347 cites W2951004968 @default.
• W2951952347 cites W2951548327 @default.
• W2951952347 cites W2951590555 @default.
• W2951952347 cites W2951638509 @default.
• W2951952347 cites W2952632681 @default.
• W2951952347 cites W2952863374 @default.
• W2951952347 cites W2953106684 @default.
• W2951952347 cites W2953259386 @default.
• W2951952347 cites W2953391683 @default.
• W2951952347 cites W2963709863 @default.
• W2951952347 cites W2963733622 @default.
• W2951952347 cites W630242894 @default.
• W2951952347 hasPublicationYear "2018" @default.
• W2951952347 type Work @default.
• W2951952347 sameAs 2951952347 @default.
• W2951952347 citedByCount "9" @default.
• W2951952347 countsByYear W29519523472018 @default.
• W2951952347 countsByYear W29519523472019 @default.
• W2951952347 countsByYear W29519523472020 @default.
• W2951952347 countsByYear W29519523472021 @default.
• W2951952347 crossrefType "posted-content" @default.
• W2951952347 hasAuthorship W2951952347A5070714354 @default.
• W2951952347 hasAuthorship W2951952347A5070940574 @default.
• W2951952347 hasConcept C101738243 @default.
• W2951952347 hasConcept C108583219 @default.
• W2951952347 hasConcept C111919701 @default.
• W2951952347 hasConcept C115961682 @default.
• W2951952347 hasConcept C11727466 @default.
• W2951952347 hasConcept C118505674 @default.
• W2951952347 hasConcept C119857082 @default.
• W2951952347 hasConcept C120665830 @default.
• W2951952347 hasConcept C121332964 @default.
• W2951952347 hasConcept C138885662 @default.
• W2951952347 hasConcept C153180895 @default.
• W2951952347 hasConcept C154945302 @default.
• W2951952347 hasConcept C192209626 @default.
• W2951952347 hasConcept C2776401178 @default.
• W2951952347 hasConcept C2779803651 @default.
• W2951952347 hasConcept C31972630 @default.
• W2951952347 hasConcept C41008148 @default.
• W2951952347 hasConcept C41895202 @default.
• W2951952347 hasConcept C52622490 @default.
• W2951952347 hasConcept C59404180 @default.
• W2951952347 hasConcept C76155785 @default.
• W2951952347 hasConcept C94915269 @default.
• W2951952347 hasConceptScore W2951952347C101738243 @default.
• W2951952347 hasConceptScore W2951952347C108583219 @default.
• W2951952347 hasConceptScore W2951952347C111919701 @default.
• W2951952347 hasConceptScore W2951952347C115961682 @default.
• W2951952347 hasConceptScore W2951952347C11727466 @default.
• W2951952347 hasConceptScore W2951952347C118505674 @default.
• W2951952347 hasConceptScore W2951952347C119857082 @default.
• W2951952347 hasConceptScore W2951952347C120665830 @default.
• W2951952347 hasConceptScore W2951952347C121332964 @default.
• W2951952347 hasConceptScore W2951952347C138885662 @default.
• W2951952347 hasConceptScore W2951952347C153180895 @default.
• W2951952347 hasConceptScore W2951952347C154945302 @default.
• W2951952347 hasConceptScore W2951952347C192209626 @default.
• W2951952347 hasConceptScore W2951952347C2776401178 @default.
• W2951952347 hasConceptScore W2951952347C2779803651 @default.
• W2951952347 hasConceptScore W2951952347C31972630 @default.
• W2951952347 hasConceptScore W2951952347C41008148 @default.
• W2951952347 hasConceptScore W2951952347C41895202 @default.
• W2951952347 hasConceptScore W2951952347C52622490 @default.

• next